Tengrui Qu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Tengrui Qu has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Kai Liu
National & Local Joint Engineering Research Center of Harbor Oil & Gas Storage and Transportation Technology, Zhejiang Key Laboratory of Pollution Control for Port-Petrochemical Industry, Zhejiang Key Laboratory of Petrochemical Environmental Pollution Control, School of Petrochemical Engineering & Environment, Zhejiang Ocean University, Zhoushan 316022, China
1 shared publication - Minjuan Wang
National & Local Joint Engineering Research Center of Harbor Oil & Gas Storage and Transportation Technology, Zhejiang Key Laboratory of Pollution Control for Port-Petrochemical Industry, Zhejiang Key Laboratory of Petrochemical Environmental Pollution Control, School of Petrochemical Engineering & Environment, Zhejiang Ocean University, Zhoushan 316022, China
1 shared publication - Siyan Hong
National & Local Joint Engineering Research Center of Harbor Oil & Gas Storage and Transportation Technology, Zhejiang Key Laboratory of Pollution Control for Port-Petrochemical Industry, Zhejiang Key Laboratory of Petrochemical Environmental Pollution Control, School of Petrochemical Engineering & Environment, Zhejiang Ocean University, Zhoushan 316022, China
1 shared publication - Ting Pan
China Petroleum Pipeline Research Institute Co., Ltd., Langfang 065000, China
1 shared publication - Xiao Cen
School of Safety and Marine Engineering, China University of Petroleum (Beijing), Beijing 102249, China
1 shared publication - Xingyu Wang
National & Local Joint Engineering Research Center of Harbor Oil & Gas Storage and Transportation Technology, Zhejiang Key Laboratory of Pollution Control for Port-Petrochemical Industry, Zhejiang Key Laboratory of Petrochemical Environmental Pollution Control, School of Petrochemical Engineering & Environment, Zhejiang Ocean University, Zhoushan 316022, China
1 shared publication
Latest Publications
- Open Access
Leakage Concentration Prediction and Interpretable Analysis of Buried Pipelines Based on Multi-Layer Perceptron and Interval Sampling
Buried-pipeline leakage poses significant safety risks, yet traditional CFD (Computational Fluid Dynamics) simulations are too slow for real-time diagnosis. This study integrates machine learning with interval sampling to develop a fast and interpretable prediction method. From 1.4 billion CFD-generated data points, 140 million representative samples were extracted via 1:10 interval sampling. Using 17 physical features as inputs, we trained and compared XGBoost, LightGBM, and a Multi-Layer Perceptron (MLP). The MLP model demonstrated exceptional performance (R2 (R-squared) = 0.9988, RMSE (Root Mean Square Error) = 0.0153), significantly outperforming the tree-based models (R2 ≈ 0.93). Three independent sampling runs confirmed its robustness (R2 coefficient of variation~0%). SHAP (Shapley Additive Explanations) analysis identified spatial coordinates and leak aperture as the most critical factors, while also revealing the nonlinear influence of soil particle size. This approach offers a high-precision, interpretable, and efficient surrogate model for buried-pipeline leakage warning systems.
Open AccessLeakage Concentration Prediction and Interpretable Analysis of Buried Pipelines Based on Multi-Layer Perceptron and Interval Sampling
Buried-pipeline leakage poses significant safety risks, yet traditional CFD (Computational Fluid Dynamics) simulations are too slow for real-time diagnosis. This study integrates machine learning with interval sampling to develop a fast and interpretable prediction method. From 1.4 billion CFD-generated data points, 140 million representative samples were extracted via 1:10 interval sampling. Using 17 physical features as inputs, we trained and compared XGBoost, LightGBM, and a Multi-Layer Perceptron (MLP). The MLP model demonstrated exceptional performance (R2 (R-squared) = 0.9988, RMSE (Root Mean Square Error) = 0.0153), significantly outperforming the tree-based models (R2 ≈ 0.93). Three independent sampling runs confirmed its robustness (R2 coefficient of variation~0%). SHAP (Shapley Additive Explanations) analysis identified spatial coordinates and leak aperture as the most critical factors, while also revealing the nonlinear influence of soil particle size. This approach offers a high-precision, interpretable, and efficient surrogate model for buried-pipeline leakage warning systems.